{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179},{"id":"1803.01442","title":"Stochastic Activation Pruning for Robust Adversarial Defense","created":"2018-03-05","cited_by_count":171},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"2109.04404","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","created":"2021-09-09","cited_by_count":156},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81},{"id":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79},{"id":"2002.11794","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","created":"2020-02-26","cited_by_count":67},{"id":"2212.14402","title":"GPT Takes the Bar Exam","created":"2022-12-29","cited_by_count":65},{"id":"2212.09095","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","created":"2022-12-18","cited_by_count":64},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59},{"id":"2205.11380","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","created":"2022-05-23","cited_by_count":55},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41},{"id":"2302.14623","title":"Fast as CHITA: Neural Network Pruning with Combinatorial Optimization","created":"2023-02-28","cited_by_count":40},{"id":"2006.08643","title":"On the training dynamics of deep networks with $L_2$ regularization","created":"2020-06-15","cited_by_count":39},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38},{"id":"2201.13096","title":"SPDY: Accurate Pruning with Speedup Guarantees","created":"2022-01-31","cited_by_count":36},{"id":"2011.04393","title":"Positional Artefacts Propagate Through Masked Language Model Embeddings","created":"2020-11-09","cited_by_count":35},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31},{"id":"1807.09810","title":"Coreset-Based Neural Network Compression","created":"2018-07-25","cited_by_count":27},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26},{"id":"2305.18383","title":"A Three-regime Model of Network Pruning","created":"2023-05-28","cited_by_count":15},{"id":"1611.06211","title":"NoiseOut: A Simple Way to Prune Neural Networks","created":"2016-11-18","cited_by_count":9},{"id":"2305.12394","title":"Pruning Pre-trained Language Models with Principled Importance and Self-regularization","created":"2023-05-21","cited_by_count":2},{"id":"1804.10223","title":"Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-Chip","created":"2018-04-26","cited_by_count":1}],"next_cursor":null}